34 citations · 73 across the 10 of their papers we have counts for
10 papers
Systematic Outliers in Large Language Models
Yongqi An, Xu Zhao, Tao Yu +2
Outliers have been widely observed in Large Language Models (LLMs), significantly impacting model performance and posing challenges for model compression. Understanding the functio…
Fluctuation-based Adaptive Structured Pruning for Large Language Models
Yongqi An, Xu Zhao, Tao Yu +2
Network Pruning is a promising way to address the huge computing resource demands of the deployment and inference of Large Language Models (LLMs). Retraining-free is important for…
Fast Segment Anything
Xu Zhao, Wenchao Ding, Yongqi An +5
The recently proposed segment anything model (SAM) has made a significant influence in many computer vision tasks. It is becoming a foundation step for many high-level tasks, like…
FreConv: Frequency Branch-and-Integration Convolutional Networks
Zhaowen Li, Xu Zhao, Peigeng Ding +4
Recent researches indicate that utilizing the frequency information of input data can enhance the performance of networks. However, the existing popular convolutional structure is…
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
Yongqi An, Xu Zhao, Tao Yu +4
Background subtraction (BGS) aims to extract all moving objects in the video frames to obtain binary foreground segmentation masks. Deep learning has been widely used in this field…
Transfering Low-Frequency Features for Domain Adaptation
Zhaowen Li, Xu Zhao, Chaoyang Zhao +2
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision. The images or feature maps of differe…
ETAD: Training Action Detection End to End on a Laptop
Shuming Liu, Mengmeng Xu, Chen Zhao +2
Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an…
Pruning-aware Sparse Regularization for Network Pruning
Nanfei Jiang, Xu Zhao, Chaoyang Zhao +3
Structural neural network pruning aims to remove the redundant channels in the deep convolutional neural networks (CNNs) by pruning the filters of less importance to the final outp…
CoupleNet: Coupling Global Structure with Local Parts for Object Detection
Yousong Zhu, Chaoyang Zhao, Jinqiao Wang +3
The region-based Convolutional Neural Network (CNN) detectors such as Faster R-CNN or R-FCN have already shown promising results for object detection by combining the region propos…
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
Xu Zhao, Yingying Chen, Ming Tang +1
Foreground segmentation in video sequences is a classic topic in computer vision. Due to the lack of semantic and prior knowledge, it is difficult for existing methods to deal with…